# FlameVQA: A Physically-Grounded UAV Wildfire VQA Benchmark with Radiometric Thermal Supervision

arXiv: https://arxiv.org/abs/2606.27128 · HTML: https://mlsanity.com/paper/2606.27128/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 13 references that are in the map.
- First posted on arXiv 25 Jun 2026.

## Builds on (most cited first, 10 of 10)

- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [HRVQA: A Visual Question Answering Benchmark for High-Resolution Aerial Images](https://mlsanity.com/paper/2301.09460/) (2023)
- [FLAME 3 Dataset: Unleashing the Power of Radiometric Thermal UAV Imagery for Wildfire Management](https://mlsanity.com/paper/2412.02831/) (2024)
- [Visual Question Answering on Multiple Remote Sensing Image Modalities](https://mlsanity.com/paper/2505.15401/) (2025)
- [Agentic AI in Remote Sensing: Foundations, Taxonomy, and Emerging Systems](https://mlsanity.com/paper/2601.01891/) (2026)
- [Style-Pro: Style-Guided Prompt Learning for Generalizable Vision-Language Models](https://mlsanity.com/paper/2411.16018/) (2024)
- [DiSa: Directional Saliency-Aware Prompt Learning for Generalizable Vision-Language Models](https://mlsanity.com/paper/2505.19373/) (2025)
- [Seeing Heat with Color -- RGB-Only Wildfire Temperature Inference from SAM-Guided Multimodal Distillation using Radiometric Ground Truth](https://mlsanity.com/paper/2505.01638/) (2025)

## Built on by (most cited first, 1 of 1)

- [AI4Fire: Evaluating Large Language Models on Wildfire Tasks](https://mlsanity.com/paper/2610.10946/) (2026)

## Abstract (arXiv)

Wildfire monitoring from UAVs requires reliable reasoning over complex aerial scenes, where smoke, scale variation, and occlusions often limit RGB-only interpretation. We introduce FlameVQA, a multiple-choice visual question answering benchmark for UAV-based wildfire intelligence built on FLAME 3, leveraging paired RGB imagery and radiometric thermal TIFFs for temperature-grounded, safety-critical reasoning. FlameVQA includes 34 multiple-choice questions per image spanning six operational capability groups, covering tasks such as detection, localization, distribution/coverage estimation, cross-modal reasoning, and flight planning. To ensure label reliability, we combine MLLM-assisted annotation with deterministic thermal rules and cross-question consistency checks, followed by human auditing. We also evaluate representative MLLMs on FlameVQA to provide baselines for future work. Results show strong performance when explicit cross-modal cues are available, but notable failures on presence detection under heavy smoke and on coverage estimation. These findings suggest that current MLLMs require domain-specific adaptation to better support disaster and wildfire monitoring. The dataset and benchmark code are open-source at github.com/mobiiin/WildFire_VQA